2017 12th System of Systems Engineering Conference (SoSE) 2017
DOI: 10.1109/sysose.2017.7994968
|View full text |Cite
|
Sign up to set email alerts
|

Pedestrian detection system for smart communities using deep Convolutional Neural Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
4
1

Relationship

1
9

Authors

Journals

citations
Cited by 27 publications
(6 citation statements)
references
References 12 publications
0
6
0
Order By: Relevance
“…Lwoski et al presented a state of the art regional detection system that utilized deep convolution networks to provide real-time pedestrian detection. Their approach achieved an accuracy of 95.7%, while at the same time managed to be simple and fast thus making it suitable for real time deployment (Lwowski et al, 2017). Genetic algorithms have also been used in the past for providing effective smart city solutions, and are the computational backbone of very recent research efforts.…”
Section: Smart City Projectsmentioning
confidence: 99%
“…Lwoski et al presented a state of the art regional detection system that utilized deep convolution networks to provide real-time pedestrian detection. Their approach achieved an accuracy of 95.7%, while at the same time managed to be simple and fast thus making it suitable for real time deployment (Lwowski et al, 2017). Genetic algorithms have also been used in the past for providing effective smart city solutions, and are the computational backbone of very recent research efforts.…”
Section: Smart City Projectsmentioning
confidence: 99%
“…Efficient mapping is a crucial process that gives rise to accurate localization and driving decision making. Usage of LiDARs for mapping is beneficial as they are well known for their high-speed and long-range sensing and hence long-range mapping, while cameras RGB, and RGB-Depth are used for short-range mapping and also used to efficiently detect obstacles [170], pedestrians [171,172], etc. There are various mapping techniques of which topological, metric, and hybrid are more useful than others and hence highlighted in this survey.…”
Section: Mappingmentioning
confidence: 99%
“…In [43], authors detect pedestrian movement and direction of movement, using a CNN based on conventional detection techniques of histograms of oriented gradients. Noting the performance deficiency in conventional CNN, a fast regional detection cascaded with CNN for real-time pedestrian detection is proposed in [44], with 97.5% accuracy at 15 frames per second, without a Graphical Processing Unit (GPU). An intelligent framework based on deep learning with the use of multiple sources of local patterns and depth information for on-road vehicle and pedestrian detection, recognition, and tracking is proposed in [45].…”
Section: B Transportmentioning
confidence: 99%